Surround-View Fisheye BEV-Perception for Valet Parking: Dataset, Baseline and Distortion-Insensitive Multi-Task Framework

Surround-view fisheye perception under valet parking scenes is fundamental and crucial in autonomous driving. Environmental conditions in parking lots perform differently from the common public datasets, such as the imperfect light and opacity, which substantially impacts on perception performance. Most existing networks based on public datasets may generalize suboptimal results on these valet parking scenes, also affected by the fisheye distortion. In this article, the authors introduce a new large-scale fisheye dataset called Fisheye Parking Dataset (FPD) to promote the research in dealing with diverse real-world surround-view parking cases. Notably, the authors' compiled FPD exhibits excellent characteristics for different surround-view perception tasks. In addition, the authors also propose their real-time distortion-insensitive multi-task framework Fisheye Perception Network (FPNet), which improves the surround-view fisheye BEV perception by enhancing the fisheye distortion operation and multi-task lightweight designs. Extensive experiments validate the effectiveness of their approach and the dataset's exceptional generalizability.

• Record URL:
  • http://dx.doi.org/10.1109/TIV.2022.3218594
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/23798858
• Supplemental Notes:
  • Copyright © 2023, IEEE.
• Authors:
  • Wu, Zizhang
  • Gan, Yuanzhu
  • Li, Xianzhi
  • Wu, Yunzhe
  • Wang, Xiaoquan
  • Xu, Tianhao
  • Wang, Fan
• Publication Date: 2023-3

Language

• English

Media Info

• Media Type: Web
• Features: Figures; References;
• Pagination: pp 2037-2048
• Serial:
  • IEEE Transactions on Intelligent Vehicles
  • Volume: 8
  • Issue Number: 3
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 2379-8858
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7274857

Subject/Index Terms

• TRT Terms: Autonomous vehicles; Cameras; Distortion (Optics); Parking; Perception; Proximity detectors
• Subject Areas: Data and Information Technology; Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01900061
• Record Type: Publication
• Files: TRIS
• Created Date: Nov 20 2023 9:12AM